AI research papers.

Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions.

On-policy distillation (OPD) has recently emerged as a promising post-training paradigm in which the student learns from trajectories generated by its own policy under dense teacher supervision.

Evaluating the physical consistency of generated videos remains a fundamental challenge.

We introduce LoopVL to study whether Loop Transformers can be effectively extended to vision- language models.

Frontier LLMs are increasingly used to automate scientific research through iterative search.

Text-conditioned full-body human-object interaction (HOI) generation requires synthesizing human motion and object trajectories that match the input text while remaining precisely coordinated over time.

GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning.

Instruction-guided video editing has made significant progress, yet existing methods use multimodal large language models (MLLMs) primarily as semantic encoders, so they often fall short in working with implicit edits th…

World models, game simulators, and long-take video creation require coherent scene evolution and sustained dynamics over extended durations.

Existing Large Language Model (LLM) routing methods score LLMs independently to select top-k models.

Skills are external artifacts that Large Language Models (LLMs) consume at inference time to improve their performance on specialized domains by incorporating relevant procedural and domain knowledge.

Unified Multimodal Models (UMMs) often rely on separate visual representations for understanding and generation, increasing visual context length and complicating integration with established vision-language pretraining…

Recent advances in musculoskeletal modeling and reinforcement learning have enabled muscle-actuated agents to reproduce increasingly complex human motions.

Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style.

Scientific coding agents receive equations, boundary conditions, and output requirements in writing, then must assess the programs they revise.

Research agents explain planned experiments.

Backdoor attacks can be implanted in Large Language Models (LLMs) during training, causing unwanted behaviour when a trigger appears in the input.

Self-driving laboratories (SDLs) aim to automate the full experimental loop, from scientific decision-making to physical execution.

On-policy distillation (OPD) improves language-model by supervising a student on prefixes sampled from its own policy, but its supervision remains confined to the output space.

Multi-agent systems (MAS) based on large language models (LLMs) have become a powerful way to address complex problems, and their effectiveness depends critically on the collaboration topology that decides which agents p…

Since launching a year ago, the Microsoft Research Asia — Singapore lab has established a strong foundation, deepened collaboration across government, academia, and industry, and explored how frontier AI research can cre…

Diffusion models can produce striking images and videos, but they still struggle with the compositional details that make a generation faithful to a prompt, such as object counts, attribute binding, spatial relations, an…

Large language models (LLMs) are increasingly embedded in educational, professional, and public infrastructure, yet widely used platforms expose "English (US)" as a primary English setting despite the global diversity of…

Prediction of wildfire occurrence is a rare-event problem compounded by spatial heterogeneity and temporal distribution shift, as fire occurrences are vastly outnumbered by non-occurrences, and predictor--fire relationsh…

Learned image compression achieves competitive rate-distortion performance, but very-low-bitrate reconstruction remains challenging because the transmitted representation cannot preserve fine textures and local structure…

Test-time reinforcement learning (TTRL) enables models to improve their reasoning without relying on labeled training data, but existing approaches typically optimize a large fraction of the model parameters.

We introduce the Endless Exam, a benchmark spanning fourteen parameterised families of mathematical construction problems, with verifiable scores that distinguish progress before and beyond published mathematical frontie…

Video world models achieve long-range temporal consistency by storing KV cache during generation, but the growing cache makes KV cache memory a major deployment bottleneck, which motivates low-bit quantization study for…

Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference expensive.

Multi-LoRA agent systems enable efficient role specialization by sharing a common backbone model.

Prompt-specialized multi-agent systems enable multiple agents to share a model while performing complementary roles to solve complex tasks.

Names are personal identifiers, but they also carry social meaning and are widely used to evaluate how language models treat different people.

Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert pool, making expert-weight traffic a major bottleneck.

This monograph develops a unified account of training and inference in Power Law Decoder Representation language models (PLDR-LLMs).

Host-resident layer streaming enables full-parameter LLM fine-tuning beyond GPU memory, but data-parallel ranks compete for shared host resources.

Does conversational memory need LLM-extracted facts, or is selecting the right raw turns enough?

Guard models support the safe deployment of language model agents, but fixed risk taxonomies limit their ability to accommodate requirements that vary across applications and tasks.

Frontier models can now perform well on individual embodied navigation tasks through multi-round multimodal reasoning with simple tools.

How much of a running workflow should a language model agent revise?

Video-language models are increasingly used as judges of video understanding, both for evaluating model outputs and for training reward models.

Scaling test-time computation is a powerful way to improve language-model reasoning, and is particularly appealing for small reasoning models (sRMs) that are cheap to serve.

Video and audio are perceived together, yet most generative models treat them in isolation.

Language model agents serving organizations must coordinate requests from multiple users while using knowledge distributed across their interactions.

We present EditWorld, a video world model for precise editing and flexible referencing in interactable worlds.

Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential for medical image understanding.

Language-model agents increasingly use tools to act on external systems.

Open-vocabulary semantic segmentation (OVSS) enables pixel-level prediction over arbitrary text-specified vocabularies and has shown strong generalization on common benchmarks.

Latent visual reasoning (LVR) enables multimodal large language models (MLLMs) to perform intermediate computation in continuous latent tokens rather than expressing every reasoning step in words.

Reinforcement learning (RL) is increasingly used to post-train vision-language-action (VLA) models, yet how RL reshapes these policies remains poorly understood.

Multi-teacher on-policy distillation (MOPD) has emerged as a popular post-training paradigm for integrating specialized capabilities in frontier language models.